Welcome
Welcome to the Computer Vision Group at RWTH Aachen University!
The Computer Vision group has been established at RWTH Aachen University in context with the Cluster of Excellence "UMIC - Ultra High-Speed Mobile Information and Communication" and is associated with the Chair Computer Sciences 8 - Computer Graphics, Computer Vision, and Multimedia. The group focuses on computer vision applications for mobile devices and robotic or automotive platforms. Our main research areas are visual object recognition, tracking, self-localization, 3D reconstruction, and in particular combinations between those topics.
We offer lectures and seminars about computer vision and machine learning.
You can browse through all our publications and the projects we are working on.
Important information for the Wintersemester 2023/2024: Unfortunately the following lectures are not offered in this semester: a) Computer Vision 2 b) Advanced Machine Learning
News
• |
WACV'25 Our work "Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think" has been accepted at WACV'25. |
Nov. 18, 2024 |
• |
IROS'24 Our work "Look Gauss, No Pose: Novel View Synthesis using Gaussian Splatting without Accurate Pose Initialization" has been accepted at IROS'24. |
July 30, 2024 |
• |
CVPR'24 We have two papers accepted at the 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR):
We have two papers accepted at Workshops: |
Feb. 27, 2024 |
• |
ICRA'24 Our Mask4Former approach has been accepted at the 2024 International Conference on Robotics and Automation (ICRA): |
Feb. 5, 2024 |
• |
ICLR'24 Our AGILE3D approach has been accepted at the 2024 International Conference on Learning Representations (ICLR): |
Jan. 27, 2024 |
• |
GCPR'23 Two papers have been accepted for publication at the German Conference on Pattern Recognition 2023 (GCPR): |
Aug. 10, 2023 |
Recent Publications
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think Winter Conference on Computer Vision (WACV) 2025 Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state-of-the-art results, high computational demands due to multi-step inference limited its use in many scenarios. In this paper, we show that the perceived inefficiency was caused by a flaw in the inference pipeline that has so far gone unnoticed. The fixed model performs comparably to the best previously reported configuration while being more than 200x faster. To optimize for downstream task performance, we perform end-to-end fine-tuning on top of the single-step model with task-specific losses and get a deterministic model that outperforms all other diffusion-based depth and normal estimation models on common zero-shot benchmarks. We surprisingly find that this fine-tuning protocol also works directly on Stable Diffusion and achieves comparable performance to current state-of-the-art diffusion-based depth and normal estimation models, calling into question some of the conclusions drawn from prior works. |
Interactive4D: Interactive 4D LiDAR Segmentation Under Review Interactive segmentation has an important role in facilitating the annotation process of future LiDAR datasets. Existing approaches sequentially segment individual objects at each LiDAR scan, repeating the process throughout the entire sequence, which is redundant and ineffective. In this work, we propose interactive 4D segmentation, a new paradigm that allows segmenting multiple objects on multiple LiDAR scans simultaneously, and Interactive4D, the first interactive 4D segmentation model that segments multiple objects on superimposed consecutive LiDAR scans in a single iteration by utilizing the sequential nature of LiDAR data. While performing interactive segmentation, our model leverages the entire space-time volume, leading to more efficient segmentation. Operating on the 4D volume, it directly provides consistent instance IDs over time and also simplifies tracking annotations. Moreover, we show that click simulations are crucial for successful model training on LiDAR point clouds. To this end, we design a click simulation strategy that is better suited for the characteristics of LiDAR data. To demonstrate its accuracy and effectiveness, we evaluate Interactive4D on multiple LiDAR datasets, where Interactive4D achieves a new state-of-the-art by a large margin. |
Look Gauss, No Pose: Novel View Synthesis using Gaussian Splatting without Accurate Pose Initialization International Conference on Intelligent Robots and Systems (IROS) 2024 3D Gaussian Splatting has recently emerged as a powerful tool for fast and accurate novel-view synthesis from a set of posed input images. However, like most novel-view synthesis approaches, it relies on accurate camera pose information, limiting its applicability in real-world scenarios where acquiring accurate camera poses can be challenging or even impossible. We propose an extension to the 3D Gaussian Splatting framework by optimizing the extrinsic camera parameters with respect to photometric residuals. We derive the analytical gradients and integrate their computation with the existing high-performance CUDA implementation. This enables downstream tasks such as 6-DoF camera pose estimation as well as joint reconstruction and camera refinement. In particular, we achieve rapid convergence and high accuracy for pose estimation on real-world scenes. Our method enables fast reconstruction of 3D scenes without requiring accurate pose information by jointly optimizing geometry and camera poses, while achieving state-of-the-art results in novel-view synthesis. Our approach is considerably faster to optimize than most com- peting methods, and several times faster in rendering. We show results on real-world scenes and complex trajectories through simulated environments, achieving state-of-the-art results on LLFF while reducing runtime by two to four times compared to the most efficient competing method. Source code will be available at https://github.com/Schmiddo/noposegs. |